LukeLin
LukeLin
I also meet this `RuntimeError: vk::PhysicalDevice::createDeviceUnique: ErrorExtensionNotPresent` after eval, it is same with you . The error occurs after running 10 episodes on all policies
> If you have DISPLAY="" all gpus should work? It's a legacy issue of sapien2.x When I use L4, DISPLAY="" does not work for me . CUDA_VISIBLE_DEVICES=0 does not work...
> Solved it by following this [doc](https://maniskill.readthedocs.io/en/latest/user_guide/getting_started/installation.html) Thank you , could you point out which commands are the solution? My A6000 is ubuntu22.04, it shows `E: Unable to locate package...
> use `vulkan-tools` instead I installed this and in H100 and it seems make my simpler env totally broken. It hang when create env` env = build_maniskill2_env( env_name, **additional_env_build_kwargs, **kwargs,...
I wonder whether I could cp /Applications/Xcode.app/Contents/Developer to /Library/Developer/CommandLineTools , Xcode hack and open every markdown, really bad Xcode.
> Hi authors, > > Thanks for your wonderful work. But I met a runtime error when I run > > CUDA_VISIBLE_DEVICES=4 python simpler_env/simple_inference_visual_matching_prepackaged_envs.py --policy rt1 \ > --ckpt-path ./checkpoints/rt_1_tf_trained_for_000400120...
It can work for me https://github.com/Stability-AI/generative-models/issues/423#issuecomment-2480263452
``` conda activate pytorch_env pip install fire omegaconf rembg pytorch_lightning kornia invisible-watermark pip install git+https://github.com/openai/CLIP.git pip install open_clip_torch pip3 install -U xformers --index-url https://download.pytorch.org/whl/cu121 pip3 install -r requirements/pt2.txt huggingface download...
issue fixed on main branch? I still meet this problem. ``` Traceback (most recent call last): File "/root/share/stable-diffusion-videos/makevideo.py", line 1, in from stable_diffusion_videos import StableDiffusionWalkPipeline ImportError: cannot import name 'StableDiffusionWalkPipeline'...
Maybe grep the log file ```python import sys from collections import deque def calculate_success_rates(log_content): stats = {} lines = log_content.strip().split('\n') i = 0 while i < len(lines) - 1: line1...